kernels-community/vllm-flash-attn3

[!CAUTION] Starting from September 13, 2026, we will be removing the "model" type repositories of kernels (e.g., kernels-community/flash-attn3). Make sure you're using a latest version of kernels. If you face any disruption, please report them here: https://github.com/huggingface/kernels/issues/new.

This is the repository card of kernels-community/vllm-flash-attn3 that has been pushed on the Hub. It was built to be used with the `kernels` library. This card was automatically generated.

How to use

# make sure `kernels` is installed: `pip install -U kernels`
from kernels import get_kernel

kernel_module = get_kernel("kernels-community/vllm-flash-attn3", version=1)
flash_attn_combine = kernel_module.flash_attn_combine

flash_attn_combine(...)

Available functions

• —flash_attn_combine
• —flash_attn_func
• —flash_attn_qkvpacked_func
• —flash_attn_varlen_func
• —flash_attn_with_kvcache
• —get_scheduler_metadata

Benchmarks

Benchmarking script is available for this kernel. Run kernels benchmark kernels-community/vllm-flash-attn3 --version 1.